Ontology Based Multiagent Effort Estimation System for Scrum Agile Method

Abstract

This paper emphasizes on software effort estimation and knowledge management of practicing Scrum methodology that are challenging tasks in agile context. Proposed approach improves software effort estimation and knowledge management of software projects by focusing on Scrum process and practices using ontology model in a multiagent estimation system. It also motivates project key stakeholders to regularly save significant tacit knowledge of unique situations in the form of lessons learnt during the project development. Various agents of the estimation system access the existing knowledge base and autonomously perform their inferencing activities using description logic as per requirements specified by the scrum master and respond with suitable estimate to him/her in the form of time, resources, and lessons learnt for the success of future projects. To validate our approach, an experiment, based on twelve web projects, was conducted using proposed approach, delphi and planning poker estimation methods. The obtained results by applying MMRE, PRED(x) evaluation measures reveals that proposed approach delivers more accurate estimates as compared with delphi and planning poker methods.